docs(p10-1a-1): wire schema + frozen design + README/HANDOFF/SMOKE + task index

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-15 17:41:26 +09:00
parent d13f58d28a
commit 7bbd2c0cbf
11 changed files with 139 additions and 8 deletions
--- a/docs/SMOKE.md
+++ b/docs/SMOKE.md
@@ -113,6 +113,11 @@ max_context_tokens = 6000

 [ui]
 theme = "dark"                       # p9-fb-14 — TUI palette ("dark" / "light", default "dark")
+
+[ingest.code]
+skip_generated_header = true
+max_file_bytes = 262144
+max_file_lines = 5000
 ```

 `KEBAB_*` 환경변수로 override 가능 (`KEBAB_MODELS_LLM_MODEL=gemma4:26b kebab …` 등). 자세한 키 목록은 `crates/kebab-config/src/lib.rs` 의 `apply_env` 매치 암. `KEBAB_READONLY=1` — write-path 비활성화 (CI 안전망). `KEBAB_PROGRESS=plain` — non-TTY 환경에서 진행 상황을 plain 한 줄씩 stderr 출력 (spinner 대신).
--- a/docs/superpowers/specs/2026-04-27-kebab-final-form-design.md
+++ b/docs/superpowers/specs/2026-04-27-kebab-final-form-design.md
@@ -37,6 +37,7 @@ related_tasks: ../../../tasks/INDEX.md
 | – | ignore | gitignore 문법 + `.kebabignore` | 익숙함 |
 | – | 에러 | thiserror per crate, anyhow at boundary | 추적성 + UX |
 | – | sync | watch=false default | v1 명시 ingest |
+| C+ | code ingest 추가 | Tier 1/2/3 fan-out, e5-large 유지, 새 Citation `code` variant | 2026-05-15 spec |

 ---

@@ -168,12 +169,12 @@ $ kebab search "Markdown chunking 규칙"

 `docs/wire-schema/v1/*.schema.json` 으로 동결. internal Rust struct ↔ wire 변환은 `From`/`TryFrom`. 모든 wire 객체는 `schema_version` 필드 필수.

-### 2.1 Citation (5 variants — discriminated by `kind`)
+### 2.1 Citation (6 variants — discriminated by `kind`)

 ```json
 {
  "schema_version": "citation.v1",
-  "kind": "line|page|region|caption|time",
+  "kind": "line|page|region|caption|time|code",
  "path": "notes/rust/kebab.md",
  "uri":  "notes/rust/kebab.md#L12-L34",

@@ -181,7 +182,20 @@ $ kebab search "Markdown chunking 규칙"
  "page":    { "page": 13, "section": "Experiment Setup" },
  "region":  { "x": 120, "y": 40, "w": 520, "h": 180 },
  "caption": { "model": "qwen2.5-vl:7b" },
-  "time":    { "start_ms": 822000, "end_ms": 850000, "speaker": "S1" }
+  "time":    { "start_ms": 822000, "end_ms": 850000, "speaker": "S1" },
+  "code":    { "start": 10, "end": 42, "lang": "rust", "repo": "kebab", "symbol": "fn ingest" }
+}
+```
+
+code variant example (p10-1A-1):
+
+```json
+{
+  "schema_version": "citation.v1",
+  "kind": "code",
+  "path": "crates/kebab-app/src/ingest.rs",
+  "uri":  "crates/kebab-app/src/ingest.rs#L10-L42",
+  "code": { "start": 10, "end": 42, "lang": "rust", "repo": "kebab", "symbol": "fn ingest" }
 }
 ```

@@ -213,7 +227,9 @@ variant 별 해당 키만 채움. `path` 와 `uri` 는 항상 채움 (`uri` 는
  },
  "index_version": "v1.0",
  "embedding_model": "multilingual-e5-large",
-  "chunker_version": "md-heading-v1"
+  "chunker_version": "md-heading-v1",
+  "repo": null,        // p10-1A-1: optional, omitted when null (code corpus only)
+  "code_lang": null    // p10-1A-1: optional, omitted when null (code corpus only)
 }
 ```

@@ -297,6 +313,17 @@ Per-query failure 는 `bulk_search_item.v1.error` (error.v1) 에 격리, 다른
  "scope": { "root": "/home/altair/KnowledgeBase", "include": ["**/*.md"], "exclude": [".git/**"] },
  "scanned": 142, "new": 12, "updated": 3, "skipped": 127, "errors": 0,
  "duration_ms": 4231,
+  "skipped_gitignore": 40,
+  "skipped_kebabignore": 5,
+  "skipped_builtin_blacklist": 80,
+  "skipped_generated": 2,
+  "skipped_size_exceeded": 1,
+  "skip_examples": {
+    "generated": ["crates/kebab-app/src/generated.rs"],
+    "size_exceeded": ["crates/kebab-app/fixtures/huge.rs"],
+    "builtin_blacklist": ["target/release/kebab"],
+    "gitignore": ["node_modules/lodash/index.js"]
+  },
  "items": [
    {
      "kind": "new|updated|skipped|error",
@@ -434,6 +461,8 @@ pub struct PromptTemplateVersion(pub String);
 pub struct SchemaVersion(pub &'static str);
 ```

+Note: `chunker_version` family extended in phase 10 (per-language pattern, see 2026-05-15 spec §3.3 for canonical list). Each new language AST chunker registers its own `ChunkerVersion` label (e.g. `code-rust-ast-v1`, `code-python-ast-v1`). The existing `md-heading-v1` / `pdf-page-v1` labels are unaffected.
+
 ### 3.3 RawAsset

 ```rust
@@ -577,6 +606,11 @@ pub struct Metadata {
    pub trust_level: TrustLevel,
    pub user_id_alias: Option<String>,
    pub user: serde_json::Map<String, serde_json::Value>,
+    // p10-1A-1: code corpus fields — None for non-code assets.
+    pub repo: Option<String>,         // git repo name (top-level dir or remote basename)
+    pub git_branch: Option<String>,   // HEAD branch name at ingest time
+    pub git_commit: Option<String>,   // HEAD commit SHA (short, 12 chars) at ingest time
+    pub code_lang: Option<String>,    // lowercase language name (e.g. "rust", "python")
 }

 pub enum SourceType { Markdown, Note, Paper, Reference, Inbox }
@@ -1370,8 +1404,11 @@ pub trait JobRepo {
 kebab-cli, kebab-tui, kebab-desktop
   └─> kebab-app
         ├─> kebab-source-fs
+         │     └─> kebab-parse-code (p10-1A-1: lang detect / repo detect / skip policy)
         ├─> kebab-parse-md / kebab-parse-pdf / kebab-parse-image / kebab-parse-audio
         │     └─> kebab-parse-types (parser intermediate)
+         ├─> kebab-parse-code
+         │     └─> kebab-core (domain types only — NO store/embed/llm/rag/UI)
         ├─> kebab-normalize
         │     └─> kebab-parse-types
         ├─> kebab-chunk
@@ -1555,6 +1592,8 @@ agent 가 분기). HTTP-SSE transport 는 fb-29 deferral 따라 P+. classify
 - real-time collab
 - enterprise auth

+코드 ingest 는 더 이상 비-스코프 아님 (2026-05-15 spec). 단 multi-workspace / watch mode / history aware (git blame 기반 citation, diff-aware re-chunking) 는 그대로 비-스코프.
+
 ---

 ## 12. 다음 단계
--- a/docs/wire-schema/v1/citation.schema.json
+++ b/docs/wire-schema/v1/citation.schema.json
@@ -7,7 +7,7 @@
  "required": ["schema_version", "kind", "path", "uri", "indexed_at", "stale"],
  "properties": {
    "schema_version": { "const": "citation.v1" },
-    "kind": { "enum": ["line", "page", "region", "caption", "time"] },
+    "kind": { "enum": ["line", "page", "region", "caption", "time", "code"] },
    "path": { "type": "string" },
    "uri":  { "type": "string" },
    "line":    { "type": "object" },
@@ -15,6 +15,7 @@
    "region":  { "type": "object" },
    "caption": { "type": "object" },
    "time":    { "type": "object" },
+    "code":    { "type": "object" },
    "indexed_at": { "type": "string", "format": "date-time" },
    "stale":      { "type": "boolean" }
  }
--- a/docs/wire-schema/v1/ingest_report.schema.json
+++ b/docs/wire-schema/v1/ingest_report.schema.json
@@ -38,6 +38,20 @@
      },
      "description": "p9-fb-25: per-extension skip count. Key = lowercase extension without leading dot (e.g. 'docx'). Files without extension key under '<no-ext>'."
    },
-    "items":          { "type": ["array", "null"] }
+    "items":          { "type": ["array", "null"] },
+    "skipped_gitignore":         { "type": "integer", "minimum": 0 },
+    "skipped_kebabignore":       { "type": "integer", "minimum": 0 },
+    "skipped_builtin_blacklist": { "type": "integer", "minimum": 0 },
+    "skipped_generated":         { "type": "integer", "minimum": 0 },
+    "skipped_size_exceeded":     { "type": "integer", "minimum": 0 },
+    "skip_examples": {
+      "type": "object",
+      "properties": {
+        "generated":         { "type": "array", "items": { "type": "string" }, "maxItems": 5 },
+        "size_exceeded":     { "type": "array", "items": { "type": "string" }, "maxItems": 5 },
+        "builtin_blacklist": { "type": "array", "items": { "type": "string" }, "maxItems": 5 },
+        "gitignore":         { "type": "array", "items": { "type": "string" }, "maxItems": 5 }
+      }
+    }
  }
 }
--- a/docs/wire-schema/v1/schema.schema.json
+++ b/docs/wire-schema/v1/schema.schema.json
@@ -78,6 +78,16 @@
          "type": "integer",
          "minimum": 0,
          "description": "p9-fb-37: docs whose updated_at exceeds config.search.stale_threshold_days. 0 when threshold=0."
+        },
+        "code_lang_breakdown": {
+          "type": "object",
+          "description": "p10-1A-1: per-language code chunk count. Key = lowercase language name (e.g. 'rust', 'python'). Populated after 1A-2 lands; empty on markdown-only corpora.",
+          "additionalProperties": { "type": "integer", "minimum": 0 }
+        },
+        "repo_breakdown": {
+          "type": "object",
+          "description": "p10-1A-1: per-repo code chunk count. Key = repo name as detected by kebab-parse-code::repo. Empty on markdown-only corpora.",
+          "additionalProperties": { "type": "integer", "minimum": 0 }
        }
      }
    }
--- a/docs/wire-schema/v1/search_hit.schema.json
+++ b/docs/wire-schema/v1/search_hit.schema.json
@@ -42,6 +42,8 @@
    "embedding_model": { "type": ["string", "null"] },
    "chunker_version": { "type": "string" },
    "indexed_at":      { "type": "string", "format": "date-time" },
-    "stale":           { "type": "boolean" }
+    "stale":           { "type": "boolean" },
+    "repo":            { "type": ["string", "null"] },
+    "code_lang":       { "type": ["string", "null"] }
  }
 }